Borrowing it
Nothing to install: this file belongs to Terry-Mao/AICodingFlow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Terry-Mao/AICodingFlow/main/.github/skills/security-review-pr/SKILL.mdgit clone --depth 1 https://github.com/Terry-Mao/AICodingFlowWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/terry-mao/aicodingflow/security-review-pr)<a href="https://agentmods.dev/skills/terry-mao/aicodingflow/security-review-pr"><img src="https://agentmods.dev/badge/skills/terry-mao/aicodingflow/security-review-pr/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/terry-mao/aicodingflow/security-review-pr"><img src="https://agentmods.dev/badge/skills/terry-mao/aicodingflow/security-review-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00066 | $0.00913 |
| Opus 5.5 | $0.00026 | $0.00365 |
| Sonnet 5.5 | $0.00013 | $0.00183 |
| Haiku 4.5 | $0.00007 | $0.00091 |
Grade A, and why
security-review-pr scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Review PR Skill
Audit the current pull request for code-level security concerns and fold any
findings into the same review.json produced by review-pr.
Required Contract
Read .agents/contracts/review.md and follow it exactly. This skill is a
supplement to review-pr; it must not create a separate report, change the
review.json schema, loosen diff-line targeting, post to GitHub, call external
security APIs, or regenerate snapshots.
When To Apply
- Apply on code and mixed PRs whenever
review-pris applied. - Do not apply on spec-only PRs handled by
review-spec. - Skip the skill when no changed file introduces code or configuration touching the concerns below.
- Do not duplicate findings the base
review-prpass will already raise.
Security Concerns
Evaluate each changed hunk against these concerns. Treat the list as a checklist, not a ceiling; flag other clearly security-relevant issues when they appear.
Input Validation And Untrusted Data
- User-supplied or network-supplied input used without validation, length limits, or type checks.
- Deserialization of untrusted data, including
pickle,yaml.load,eval,Function, or parsed JSON flowing into commands. - Path traversal from user input concatenated into filesystem paths without normalization or an allowlist.
- SSRF from user-controlled URLs passed to outbound HTTP clients without scheme or host restrictions.
- Unbounded resource use driven by untrusted input.
Output Encoding And Sanitization
- Untrusted data interpolated into SQL, shell commands, HTML, Markdown, log lines, or URLs without proper encoding or parameterization.
- Use of
shell=True, string concatenation into process execution, or raw SQL strings. - Rendering user-supplied Markdown or HTML without sanitization.
Authentication And Authorization
- Missing or weakened authentication on new endpoints, RPC handlers, workflow triggers, or CLI commands.
- Authorization checks that trust client-supplied identifiers instead of the authenticated principal.
- Permission checks removed or made more permissive without clear justification.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 99 lines · 66 tokens per session scan A 739c851b0182
security-review-pr is a skill published in the GitHub repository Terry-Mao/AICodingFlow (169 stars, last pushed today), licensed MIT. It adds 66 tokens to every session and 913 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…